Add TFHubAudioExtractor + SPICE Tests

[adelavega]

• Adds TFHubAudioExtractor This extractor is very similar to TFHubImageExtractor but with 1) slightly different preprocessing 2) infers timing output of model (i.e. onsets, durations) from the output (assumes fixed sampling rate)
• Adds saved_model loading to TFHubExtractor. Models like SPICE are not meant to instantiated as KerasLayer. Instead, they must be loaded with hub.load and have predefined signature where the model is stores, and named vectors as outputs.

For reference this is the SPICE model: https://tfhub.dev/google/spice/

[codecov-commenter]

Codecov Report

Base: 75.11% // Head: 75.27% // Increases project coverage by +0.15% :tada:

Coverage data is based on head (d92c637) compared to base (ecdf208). Patch coverage: 97.61% of modified lines in pull request are covered.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## master #485 +/- ## ========================================== + Coverage 75.11% 75.27% +0.15% ========================================== Files 59 59 Lines 3866 3886 +20 ========================================== + Hits 2904 2925 +21 + Misses 962 961 -1 ``` | [Impacted Files](https://codecov.io/gh/PsychoinformaticsLab/pliers/pull/485?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab) | Coverage Δ | | |---|---|---| | [pliers/extractors/models.py](https://codecov.io/gh/PsychoinformaticsLab/pliers/pull/485/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab#diff-cGxpZXJzL2V4dHJhY3RvcnMvbW9kZWxzLnB5) | `94.73% <97.61%> (+0.89%)` | :arrow_up: | | [pliers/converters/base.py](https://codecov.io/gh/PsychoinformaticsLab/pliers/pull/485/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab#diff-cGxpZXJzL2NvbnZlcnRlcnMvYmFzZS5weQ==) | `90.62% <0.00%> (-3.13%)` | :arrow_down: | | [pliers/filters/image.py](https://codecov.io/gh/PsychoinformaticsLab/pliers/pull/485/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab#diff-cGxpZXJzL2ZpbHRlcnMvaW1hZ2UucHk=) | `98.61% <0.00%> (-0.02%)` | :arrow_down: | | [pliers/diagnostics/base.py](https://codecov.io/gh/PsychoinformaticsLab/pliers/pull/485/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab#diff-cGxpZXJzL2RpYWdub3N0aWNzL2Jhc2UucHk=) | `90.42% <0.00%> (+2.00%)` | :arrow_up: | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=PsychoinformaticsLab)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.